Home > Research > Publications & Outputs > Euclid preparation

Research

Electronic data

  • 2209.13074v1

    Accepted author manuscript, 2.15 MB, PDF document

    Available under license: CC BY

Keywords

View graph of relations

Euclid preparation: XXII. Selection of Quiescent Galaxies from Mock Photometry using Machine Learning

Research output: Contribution to Journal/Magazine › Journal article › peer-review

Forthcoming

Standard

Euclid preparation: XXII. Selection of Quiescent Galaxies from Mock Photometry using Machine Learning. / Euclid Collaboration.
In: Astronomy and Astrophysics, 15.09.2022.

Research output: Contribution to Journal/Magazine › Journal article › peer-review

Harvard

Euclid Collaboration 2022, 'Euclid preparation: XXII. Selection of Quiescent Galaxies from Mock Photometry using Machine Learning', Astronomy and Astrophysics.

APA

Euclid Collaboration (in press). Euclid preparation: XXII. Selection of Quiescent Galaxies from Mock Photometry using Machine Learning. Astronomy and Astrophysics.

Vancouver

Euclid Collaboration. Euclid preparation: XXII. Selection of Quiescent Galaxies from Mock Photometry using Machine Learning. Astronomy and Astrophysics. 2022 Sept 15.

Author

Euclid Collaboration. / Euclid preparation : XXII. Selection of Quiescent Galaxies from Mock Photometry using Machine Learning. In: Astronomy and Astrophysics. 2022.

Bibtex

@article{be21e8ac8eb8453ba1313e327e9d5137,
title = "Euclid preparation: XXII. Selection of Quiescent Galaxies from Mock Photometry using Machine Learning",
abstract = " The Euclid Space Telescope will provide deep imaging at optical and near-infrared wavelengths, along with slitless near-infrared spectroscopy, across ~15,000 sq deg of the sky. Euclid is expected to detect ~12 billion astronomical sources, facilitating new insights into cosmology, galaxy evolution, and various other topics. To optimally exploit the expected very large data set, there is the need to develop appropriate methods and software. Here we present a novel machine-learning based methodology for selection of quiescent galaxies using broad-band Euclid I_E, Y_E, J_E, H_E photometry, in combination with multiwavelength photometry from other surveys. The ARIADNE pipeline uses meta-learning to fuse decision-tree ensembles, nearest-neighbours, and deep-learning methods into a single classifier that yields significantly higher accuracy than any of the individual learning methods separately. The pipeline has `sparsity-awareness', so that missing photometry values are still informative for the classification. Our pipeline derives photometric redshifts for galaxies selected as quiescent, aided by the `pseudo-labelling' semi-supervised method. After application of the outlier filter, our pipeline achieves a normalized mean absolute deviation of ~< 0.03 and a fraction of catastrophic outliers of ~< 0.02 when measured against the COSMOS2015 photometric redshifts. We apply our classification pipeline to mock galaxy photometry catalogues corresponding to three main scenarios: (i) Euclid Deep Survey with ancillary ugriz, WISE, and radio data; (ii) Euclid Wide Survey with ancillary ugriz, WISE, and radio data; (iii) Euclid Wide Survey only. Our classification pipeline outperforms UVJ selection, in addition to the Euclid I_E-Y_E, J_E-H_E and u-I_E,I_E-J_E colour-colour methods, with improvements in completeness and the F1-score of up to a factor of 2. (Abridged) ",
keywords = "astro-ph.IM, astro-ph.GA",
author = "{Euclid Collaboration} and A. Humphrey and L. Bisigello and Cunha, {P. A. C.} and M. Bolzonella and S. Fotopoulou and K. Caputi and C. Tortora and G. Zamorani and P. Papaderos and D. Vergani and J. Brinchmann and M. Moresco and A. Amara and N. Auricchio and M. Baldi and R. Bender and D. Bonino and E. Branchini and M. Brescia and S. Camera and V. Capobianco and C. Carbone and J. Carretero and Castander, {F. J.} and M. Castellano and S. Cavuoti and A. Cimatti and R. Cledassou and G. Congedo and Conselice, {C. J.} and L. Conversi and Y. Copin and L. Corcione and F. Courbin and M. Cropper and Silva, {A. Da} and H. Degaudenzi and M. Douspis and F. Dubath and Duncan, {C. A. J.} and X. Dupac and S. Dusini and S. Farrens and S. Ferriol and M. Frailis and E. Franceschi and M. Fumana and P. Gomez-Alvarez and S. Galeotta and I. Hook",
year = "2022",
month = sep,
day = "15",
language = "English",
journal = "Astronomy and Astrophysics",
issn = "1432-0746",
publisher = "EDP Sciences",

}

RIS

TY - JOUR

T1 - Euclid preparation

T2 - XXII. Selection of Quiescent Galaxies from Mock Photometry using Machine Learning

AU - Euclid Collaboration

AU - Humphrey, A.

AU - Bisigello, L.

AU - Cunha, P. A. C.

AU - Bolzonella, M.

AU - Fotopoulou, S.

AU - Caputi, K.

AU - Tortora, C.

AU - Zamorani, G.

AU - Papaderos, P.

AU - Vergani, D.

AU - Brinchmann, J.

AU - Moresco, M.

AU - Amara, A.

AU - Auricchio, N.

AU - Baldi, M.

AU - Bender, R.

AU - Bonino, D.

AU - Branchini, E.

AU - Brescia, M.

AU - Camera, S.

AU - Capobianco, V.

AU - Carbone, C.

AU - Carretero, J.

AU - Castander, F. J.

AU - Castellano, M.

AU - Cavuoti, S.

AU - Cimatti, A.

AU - Cledassou, R.

AU - Congedo, G.

AU - Conselice, C. J.

AU - Conversi, L.

AU - Copin, Y.

AU - Corcione, L.

AU - Courbin, F.

AU - Cropper, M.

AU - Silva, A. Da

AU - Degaudenzi, H.

AU - Douspis, M.

AU - Dubath, F.

AU - Duncan, C. A. J.

AU - Dupac, X.

AU - Dusini, S.

AU - Farrens, S.

AU - Ferriol, S.

AU - Frailis, M.

AU - Franceschi, E.

AU - Fumana, M.

AU - Gomez-Alvarez, P.

AU - Galeotta, S.

AU - Hook, I.

PY - 2022/9/15

Y1 - 2022/9/15

N2 - The Euclid Space Telescope will provide deep imaging at optical and near-infrared wavelengths, along with slitless near-infrared spectroscopy, across ~15,000 sq deg of the sky. Euclid is expected to detect ~12 billion astronomical sources, facilitating new insights into cosmology, galaxy evolution, and various other topics. To optimally exploit the expected very large data set, there is the need to develop appropriate methods and software. Here we present a novel machine-learning based methodology for selection of quiescent galaxies using broad-band Euclid I_E, Y_E, J_E, H_E photometry, in combination with multiwavelength photometry from other surveys. The ARIADNE pipeline uses meta-learning to fuse decision-tree ensembles, nearest-neighbours, and deep-learning methods into a single classifier that yields significantly higher accuracy than any of the individual learning methods separately. The pipeline has `sparsity-awareness', so that missing photometry values are still informative for the classification. Our pipeline derives photometric redshifts for galaxies selected as quiescent, aided by the `pseudo-labelling' semi-supervised method. After application of the outlier filter, our pipeline achieves a normalized mean absolute deviation of ~< 0.03 and a fraction of catastrophic outliers of ~< 0.02 when measured against the COSMOS2015 photometric redshifts. We apply our classification pipeline to mock galaxy photometry catalogues corresponding to three main scenarios: (i) Euclid Deep Survey with ancillary ugriz, WISE, and radio data; (ii) Euclid Wide Survey with ancillary ugriz, WISE, and radio data; (iii) Euclid Wide Survey only. Our classification pipeline outperforms UVJ selection, in addition to the Euclid I_E-Y_E, J_E-H_E and u-I_E,I_E-J_E colour-colour methods, with improvements in completeness and the F1-score of up to a factor of 2. (Abridged)

AB - The Euclid Space Telescope will provide deep imaging at optical and near-infrared wavelengths, along with slitless near-infrared spectroscopy, across ~15,000 sq deg of the sky. Euclid is expected to detect ~12 billion astronomical sources, facilitating new insights into cosmology, galaxy evolution, and various other topics. To optimally exploit the expected very large data set, there is the need to develop appropriate methods and software. Here we present a novel machine-learning based methodology for selection of quiescent galaxies using broad-band Euclid I_E, Y_E, J_E, H_E photometry, in combination with multiwavelength photometry from other surveys. The ARIADNE pipeline uses meta-learning to fuse decision-tree ensembles, nearest-neighbours, and deep-learning methods into a single classifier that yields significantly higher accuracy than any of the individual learning methods separately. The pipeline has `sparsity-awareness', so that missing photometry values are still informative for the classification. Our pipeline derives photometric redshifts for galaxies selected as quiescent, aided by the `pseudo-labelling' semi-supervised method. After application of the outlier filter, our pipeline achieves a normalized mean absolute deviation of ~< 0.03 and a fraction of catastrophic outliers of ~< 0.02 when measured against the COSMOS2015 photometric redshifts. We apply our classification pipeline to mock galaxy photometry catalogues corresponding to three main scenarios: (i) Euclid Deep Survey with ancillary ugriz, WISE, and radio data; (ii) Euclid Wide Survey with ancillary ugriz, WISE, and radio data; (iii) Euclid Wide Survey only. Our classification pipeline outperforms UVJ selection, in addition to the Euclid I_E-Y_E, J_E-H_E and u-I_E,I_E-J_E colour-colour methods, with improvements in completeness and the F1-score of up to a factor of 2. (Abridged)

KW - astro-ph.IM

KW - astro-ph.GA

M3 - Journal article

JO - Astronomy and Astrophysics

JF - Astronomy and Astrophysics

SN - 1432-0746

ER -